37 citations · 160 across the 27 of their papers we have counts for
30 papers
Exploiting Spatial Structure for Transductive Few-Shot Classification of Whole-Slide Images
Tiffanie Godelaine, Manon Dausort, Karim El Khoury +3
Automating the analysis of whole-slide images (WSIs), a key step in cancer diagnosis, has high clinical value, as it can reduce pathologist's workload while improving diagnosis acc…
Refining Cytology Predictions with Conditional Random Fields
Manon Dausort, Tiffanie Godelaine, Karim El Khoury +3
Vision-language models (VLMs) achieve strong zero-shot (ZS) classification on histology images but do not perform as well on cytology, whose stains and cell morphology differ marke…
Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model
Ali Aouf, Eric Laloy, Bart Rogiers +1
Characterizing the physical properties of clay and cementitious materials matters across many fields, from materials science to geological waste disposal. Property simulation typic…
Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols
Tiffanie Godelaine, Maxime Zanella, Karim El Khoury +2
Automating the analysis of whole-slide images has high clinical value, since characterizing cancers requires examining them in detail. Such analysis increasingly relies on vision-l…
Locally Consistent Transductive Information Maximization for Few-Shot Remote Sensing Scene Classification
Karim El Khoury, Benoît Gérin, Benoît Macq +1
Remote sensing scene classification is increasingly relying on foundation models pre-trained on large-scale Earth-observation data. Moreover, transductive inference, which exploits…
RUMPL: Ray-Based Transformers for Universal Multi-View 2D to 3D Human Pose Lifting
Seyed Abolfazl Ghasemzadeh, Alexandre Alahi, Christophe De Vleeschouwer
Estimating 3D human poses from 2D images remains challenging due to occlusions and projective ambiguity. Multi-view learning-based approaches mitigate these issues but often fail t…
Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Models
Karim El Khoury, Maxime Zanella, Christophe De Vleeschouwer +1
Remote Sensing Vision-Language Models (RSVLMs) have shown remarkable potential thanks to large-scale pretraining, achieving strong zero-shot performance on various tasks. However,…
Data-Efficient Stream-Based Active Distillation for Scalable Edge Model Deployment
Dani Manjah, Tim Bary, Benoît Gérin +2
Edge camera-based systems are continuously expanding, facing ever-evolving environments that require regular model updates. In practice, complex teacher models are run on a central…
Sequential Representation Learning via Static-Dynamic Conditional Disentanglement
Mathieu Cyrille Simon, Pascal Frossard, Christophe De Vleeschouwer
This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos. We prop…
Keypoint Promptable Re-Identification
Vladimir Somers, Christophe De Vleeschouwer, Alexandre Alahi
Occluded Person Re-Identification (ReID) is a metric learning task that involves matching occluded individuals based on their appearance. While many studies have tackled occlusions…
Domain Generalization for 6D Pose Estimation Through NeRF-based Image Synthesis
Antoine Legrand, Renaud Detry, Christophe De Vleeschouwer
This work introduces a novel augmentation method that increases the diversity of a train set to improve the generalization abilities of a 6D pose estimation network. For this purpo…
Leveraging Neural Radiance Fields for Pose Estimation of an Unknown Space Object during Proximity Operations
Antoine Legrand, Renaud Detry, Christophe De Vleeschouwer
We address the estimation of the 6D pose of an unknown target spacecraft relative to a monocular camera, a key step towards the autonomous rendezvous and proximity operations requi…
Domain Generalization for In-Orbit 6D Pose Estimation
Antoine Legrand, Renaud Detry, Christophe De Vleeschouwer
We address the problem of estimating the relative 6D pose, i.e., position and orientation, of a target spacecraft, from a monocular image, a key capability for future autonomous Re…
Self-supervised vision-langage alignment of deep learning representations for bone X-rays analysis
Alexandre Englebert, Anne-Sophie Collin, Olivier Cornu +1
This paper proposes leveraging vision-language pretraining on bone X-rays paired with French reports to address downstream tasks of interest on bone radiography. A practical proces…
Self-Avatar Animation in Virtual Reality: Impact of Motion Signals Artifacts on the Full-Body Pose Reconstruction
Antoine Maiorca, Seyed Abolfazl Ghasemzadeh, Thierry Ravet +3
Virtual Reality (VR) applications have revolutionized user experiences by immersing individuals in interactive 3D environments. These environments find applications in numerous fie…
Multi-Stream Cellular Test-Time Adaptation of Real-Time Models Evolving in Dynamic Environments
Benoît Gérin, Anaïs Halin, Anthony Cioppa +5
In the era of the Internet of Things (IoT), objects connect through a dynamic network, empowered by technologies like 5G, enabling real-time data sharing. However, smart objects, n…
SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap
Vladimir Somers, Victor Joos, Anthony Cioppa +11
Tracking and identifying athletes on the pitch holds a central role in collecting essential insights from the game, such as estimating the total distance covered by players or unde…
Camera clustering for scalable stream-based active distillation
Dani Manjah, Davide Cacciarelli, Christophe De Vleeschouwer +1
We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques. We scrutini…
Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking
Amir M. Mansourian, Vladimir Somers, Christophe De Vleeschouwer +1
Effective tracking and re-identification of players is essential for analyzing soccer videos. But, it is a challenging task due to the non-linear motion of players, the similarity…
Context-Aware 3D Object Localization from Single Calibrated Images: A Study of Basketballs
Marcello Davide Caio, Gabriel Van Zandycke, Christophe De Vleeschouwer
Accurately localizing objects in three dimensions (3D) is crucial for various computer vision applications, such as robotics, autonomous driving, and augmented reality. This task f…
On the Importance of Denoising when Learning to Compress Images
Benoit Brummer, Christophe De Vleeschouwer
Image noise is ubiquitous in photography. However, image noise is not compressible nor desirable, thus attempting to convey the noise in compressed image bitstreams yields sub-par…
Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?
Antoine Vanderschueren, Christophe De Vleeschouwer
Turning the weights to zero when training a neural network helps in reducing the computational complexity at inference. To progressively increase the sparsity ratio in the network…
SoccerNet 2022 Challenges Results
Silvio Giancola, Anthony Cioppa, Adrien Deliège +91
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks:…
Forward Error Correction applied to JPEG-XS codestreams
Antoine Legrand, Benoît Macq, Christophe De Vleeschouwer
JPEG-XS offers low complexity image compression for applications with constrained but reasonable bit-rate, and low latency. Our paper explores the deployment of JPEG-XS on lossy pa…